Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/348996
Title: | Epsilon Focus Photography A study of Focus Defocus and Depth of Field |
Researcher: | Parikshit Vishwas Sakurikar |
Guide(s): | P J Narayanan |
Keywords: | Computer Science Computer Science Information Systems Engineering and Technology |
University: | International Institute of Information Technology, Hyderabad |
Completed Date: | 2021 |
Abstract: | Focus, defocus and depth-of-field are integral aspects of a photograph captured using a wide-aperture camera. newlineFocus and defocus blur provide critical cues for estimation of scene depth and structure which helps in newlinescene understanding or post-capture image manipulation. newlineFocus and defocus blur are also used creatively by photographers to produce remarkable newlinecompositional effects such as emphasis on the foreground subject with aesthetic bokeh in the background. newlineEpsilon Focus Photography is a branch of computational photography that deals with the capture and processing of newlinemulti-focus imagery - where multiple wide-aperture images are captured with a small change in focus position. newlineIn this thesis, we provide a comprehensive study of various problems in epsilon focus photography along with newlinea detailed analysis of the related work in the area. We provide useful constructs for the newlineunderstanding and manipulation of focus, defocus blur and the depth-of-field of an image. newline newlineThe work in this thesis can be divided into four broad categories of measurement, representation, manipulation newlineand applications of focus. Measuring focus is a long studied and challenging problem in computer vision. newlineWe study various methods to measure focus and propose a composite measure of focus that combines the strengths of well-known focus measures. newlineWe the study the task of post-capture focus manipulation at each pixel in an image and formulate a novel newlinerepresentation of focus that can find much use in image editing toolkits. newlineOur representation can faithfully encode the fine characteristics of a wide-aperture image even at complex newlineinteraction locations such as depth-edges and over-saturated background regions, while optimizing the memory newlinefootprint of multi-focus imagery. Apart from precise geometric constructs for scene refocusing, we also newlinepropose an data-driven approach for post-capture scene refocusing using deep adversarial learning. We show how the tasks of deblurring an image, newlinemagnification of the defocused content and overall comprehensive |
Pagination: | |
URI: | http://hdl.handle.net/10603/348996 |
Appears in Departments: | Computer Science and Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
80_recommendation.pdf | Attached File | 60.08 kB | Adobe PDF | View/Open |
abstract (4).pdf | 41.74 kB | Adobe PDF | View/Open | |
certificate (2).pdf | 40.38 kB | Adobe PDF | View/Open | |
chapter1-introduction.pdf | 4.03 MB | Adobe PDF | View/Open | |
chapter2-relatedwork.pdf | 3.34 MB | Adobe PDF | View/Open | |
chapter3.pdf | 16.48 MB | Adobe PDF | View/Open | |
chapter4.pdf | 14.86 MB | Adobe PDF | View/Open | |
chapter5.pdf | 22.32 MB | Adobe PDF | View/Open | |
chapter6.pdf | 8.07 MB | Adobe PDF | View/Open | |
titlepage (2).pdf | 328.81 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: